Dynamic Integrated Scheduling of Production Equipment and Automated Guided Vehicles in a Flexible Job Shop Based on Deep Reinforcement Learning

Processes, Год журнала: 2024, Номер 12(11), С. 2423 - 2423

Опубликована: Ноя. 2, 2024

The high-quality development of the manufacturing industry necessitates accelerating its transformation towards high-end, intelligent, and green development. Considering logistics resource constraints, impact dynamic disturbance events on production, need for energy-efficient integrated scheduling production equipment automated guided vehicles (AGVs) in a flexible job shop environment is investigated this study. Firstly, static model AGVs (ISPEA) developed based mixed-integer programming, which aims to optimize maximum completion time total energy consumption (EC). In recent years, reinforcement learning, including deep learning (DRL), has demonstrated significant advantages handling workshop issues with sequential decision-making characteristics, can fully utilize vast quantity historical data accumulated adjust plans timely manner changes conditions demand. Accordingly, DRL-based approach introduced address common disturbances emergency order insertions. Combined characteristics ISPEA problem an event-driven strategy events, four types agents, namely workpiece selection, machine AGV target selection are set up, refine status as observation inputs generate rules selecting workpieces, machines, AGVs, targets. These agents trained offline using QMIX multi-agent framework, utilized solve problem. Finally, effectiveness proposed method validated through comparison solution performance other typical optimization algorithms various cases.

Язык: Английский

---

Graph neural networks for job shop scheduling problems: A survey

Computers & Operations Research, Год журнала: 2024, Номер unknown, С. 106914 - 106914

Опубликована: Ноя. 1, 2024

Язык: Английский

---

A novel method for solving dynamic flexible job-shop scheduling problem via DIFFormer and deep reinforcement learning

Computers & Industrial Engineering, Год журнала: 2024, Номер 198, С. 110688 - 110688

Опубликована: Ноя. 6, 2024

Язык: Английский

---

Study on the application of single-agent and multi-agent reinforcement learning to dynamic scheduling in manufacturing environments with growing complexity: Case study on the synthesis of an industrial IoT Test Bed

Journal of Manufacturing Systems, Год журнала: 2024, Номер 77, С. 525 - 557

Опубликована: Окт. 19, 2024

Язык: Английский

---

Deep reinforcement learning-based dynamic scheduling for resilient and sustainable manufacturing: A systematic review

Journal of Manufacturing Systems, Год журнала: 2024, Номер 77, С. 962 - 989

Опубликована: Ноя. 13, 2024

Язык: Английский

---

Dynamic scheduling for multi-objective flexible job shop via deep reinforcement learning

Applied Soft Computing, Год журнала: 2025, Номер 171, С. 112787 - 112787

Опубликована: Янв. 25, 2025

Язык: Английский

---

A novel hybrid intelligent scheduling: integrating human feedback into reinforcement learning for adaptive preference objectives

International Journal of Production Research, Год журнала: 2025, Номер unknown, С. 1 - 19

Опубликована: Фев. 19, 2025

Язык: Английский

---

Discrete Multi-Objective Grey Wolf Algorithm Applied to Dynamic Distributed Flexible Job Shop Scheduling Problem with Variable Processing Times

Applied Sciences, Год журнала: 2025, Номер 15(5), С. 2281 - 2281

Опубликована: Фев. 20, 2025

Uncertainty in processing times is a key issue distributed production; it severely affects scheduling accuracy. In this study, we investigate dynamic flexible job shop problem with variable (DDFJSP-VPT), which the time follows normal distribution. First, mathematical model established by simultaneously considering makespan, tardiness, and total factory load. Second, chance-constrained approach employed to predict uncertain generate robust initial schedule. Then, heuristic method involves left-shift strategy, an insertion-based local adjustment DMOGWO-based global rescheduling strategy developed dynamically adjust plan response context of uncertainty. Moreover, hybrid initialization scheme, discrete crossover, mutation operations are designed high-quality population update wolf pack, enabling GWO effectively solve problem. Based on parameter sensitivity study comparison four algorithms, algorithm’s stability effectiveness both static environments demonstrated. Finally, experimental results show that our can achieve much better performance than other rules-based reactive methods hybrid-shift strategy. The utility prediction also validated.

Язык: Английский

---

Research on dynamic job shop scheduling problem with AGV based on DQN

Cluster Computing, Год журнала: 2025, Номер 28(4)

Опубликована: Фев. 25, 2025

Язык: Английский

---

Learn to optimise for job shop scheduling: a survey with comparison between genetic programming and reinforcement learning

Artificial Intelligence Review, Год журнала: 2025, Номер 58(6)

Опубликована: Март 15, 2025

Язык: Английский

---